Probabilistic self-learning framework for Low-dose CT Denoising

TL;DR

This paper introduces a probabilistic self-learning framework for denoising low-dose CT images that does not require paired training data, leveraging inherent pixel correlations to improve image quality.

Contribution

A novel shift-invariant neural network that learns noise and pixel correlations solely from LDCT images, reducing reliance on paired datasets.

Findings

Outperforms existing methods in denoising quality

Produces images with style similar to routine NDCT

Effective with only LDCT images for training

Abstract

Despite the indispensable role of X-ray computed tomography (CT) in diagnostic medicine field, the associated ionizing radiation is still a major concern considering that it may cause genetic and cancerous diseases. Decreasing the exposure can reduce the dose and hence the radiation-related risk, but will also induce higher quantum noise. Supervised deep learning can be used to train a neural network to denoise the low-dose CT (LDCT). However, its success requires massive pixel-wise paired LDCT and normal-dose CT (NDCT) images, which are rarely available in real practice. To alleviate this problem, in this paper, a shift-invariant property based neural network was devised to learn the inherent pixel correlations and also the noise distribution by only using the LDCT images, shaping into our probabilistic self-learning framework. Experimental results demonstrated that the proposed method outperformed the competitors, producing an enhanced LDCT image that has similar image style as the routine NDCT which is highly-preferable in clinic practice.